© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96157
    Prev
    Next
    INDEX
    Explanations

    Ger

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨåIJ§
    -0.29
    uples
    -0.29
    åħ±è¯Ĩ
    -0.28
     miracle
    -0.27
     бÑİ
    -0.24
    ny
    -0.24
    _unpack
    -0.24
    åħīæ³½
    -0.24
    á¹ĩ
    -0.24
    SES
    -0.23
    POSITIVE LOGITS
     interf
    0.29
    ión
    0.27
    atri
    0.26
    _manifest
    0.26
    etr
    0.25
     atr
    0.25
    oked
    0.24
    ahr
    0.24
    óst
    0.24
     bell
    0.24
    Activations Density 0.003%

    No Known Activations